> The issue is that PETSc does everything on a per-MPI-process basis and, to > the best of my knowledge, does not use threads itself to implement e.g. its > matvec. And threaded BLAS will only take you so far... So you could > assemble the system matrix with threads on 16 cores in a node, but when > PETSc solves the linear system I think it will only be using one core.
Yes, the PETSc people need to do some work there as well. > Wolfgang's petsc flag was new to me and I'm gonna look into it, although > this is not promising: > http://www-unix.mcs.anl.gov/petsc/petsc-2/miscellaneous/petscthreads.html That page has been there for at least 4 years. My reading is that all it says is that you can't call PETSc functions from different threads at the same time. I don't think they want to say that PETSc can't internally use threads to do its computations (and this is what we want them to do of course). I'm going to see if I can't figure out what the flag's name was. I believe it was still internal, and may only exist on PETSc dev. W. ------------------------------------------------------------------------- Wolfgang Bangerth email: [EMAIL PROTECTED] www: http://www.math.tamu.edu/~bangerth/ ------------------------------------------------------------------------- This SF.net email is sponsored by: Microsoft Defy all challenges. Microsoft(R) Visual Studio 2008. http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/ _______________________________________________ Libmesh-users mailing list Libmesh-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/libmesh-users
